Wizardlm GGUF models
127 GGUF models in the Wizardlm family, quantized by 56 uploaders. Sizes run from 1.24B to 141B parameters. The longest trained context is 64K tokens.
About the Wizardlm GGUF models
Wizardlm is represented on ggufmodels.com by 127 GGUF models, quantized by 56 uploaders on Hugging Face. The most downloaded are models--microsoft--WizardLM-2-7B, ehartford_wizardlm-7b-uncensored and WizardLM 30B Uncensored Guanaco SuperCOT 30b i1. Parameter counts run from 1.24B to 141B, and the longest trained context window is 64K tokens.
A Q4_K_M file of a Wizardlm model is between 4.1 to 85.6 GB, which is the quant most people start with. Most files come from mradermacher (33), TheBloke (13) and ysn-rfd (7). The quants you will meet most often are Q4_K_M (91), Q2_K (85), Q5_K_M (84) and Q4_K_S (80), where the number is how many models offer that quant.
Frequently asked questions
Which Wizardlm GGUF should I download?
The most downloaded Wizardlm GGUF here is models--microsoft--WizardLM-2-7B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Wizardlm model need?
Q4_K_M files of Wizardlm models on this site range from 4.1 to 85.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Wizardlm GGUF files come from?
The most common quantizers here are mradermacher, TheBloke and ysn-rfd. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.